Re: [Xen-API] OVS, CloudStack, and Crashing XenServer

[Ben Pfaff <blp@xxxxxxxxxxxxxxx>]

Clayton Weise <cweise@xxxxxxxxxx> writes:

> I have recently encountered a reproducible and rather catastrophic
> issue with OVS and XenServer caused by CloudStack.  For CloudStack,
> during the "snapshot" process with CloudStack a snapshot is created on
> the XS host, then it's copied off to an NFS share as a .vhd file via a
> specialized VM called the secondary storage VM (SSVM).
>
> If the SSVM and guest VM that is being snapshotted are on the same
> host about 4-5 GB into the copy process ovs-vswitchd consumes all
> available CPU on the host to the point that it becomes unusable and
> all management interfaces (including our 10gbit iSCSI NICs) become
> unresponsive.  I've waited over 30 minutes for this problem to correct
> itself but it never seems to.  After switching from OVS to bridged
> networking mode I have been able to successfully copy 100GB snapshots
> without issue.
>
> Any insight into this would be appreciated.  I would be happy to
> reproduce this problem and provide any logs available.

What version of Open vSwitch is this?

The usual place to report bugs in Open vSwitch is
bugs@xxxxxxxxxxxxxxxx


_______________________________________________
Xen-api mailing list
Xen-api@xxxxxxxxxxxxx
http://lists.xen.org/cgi-bin/mailman/listinfo/xen-api